Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.9231. Min Act: -0.1700
Data Index: 5782793 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.5481. Min Act: -0.1700
Data Index: 4066956 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.4856. Min Act: -0.1700
Data Index: 5861479 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2981. Min Act: -0.1700
Data Index: 245960 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2981. Min Act: -0.1700
Data Index: 311489 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2356. Min Act: -0.1700
Data Index: 1848782 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2356. Min Act: -0.1700
Data Index: 4124259 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2044. Min Act: -0.1700
Data Index: 426256 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.2044. Min Act: -0.1700
Data Index: 2815347 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.1731. Min Act: -0.1700
Data Index: 2288072 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.1419. Min Act: -0.1700
Data Index: 717175 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.1106. Min Act: -0.1700
Data Index: 5861480 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.0793. Min Act: -0.1700
Data Index: 311507 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.1106. Min Act: -0.1700
Data Index: 2279085 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9231. Min Range: -4.9231
Max Act: 4.1106. Min Act: -0.1700
Data Index: 3018402 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9231. Min Range: -4.9231
Max Act: 3.9856. Min Act: -0.1700
Data Index: 5838854 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9231. Min Range: -4.9231
Max Act: 3.9856. Min Act: -0.1700
Data Index: 4217350 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9231. Min Range: -4.9231
Max Act: 3.9543. Min Act: -0.1700
Data Index: 7662168 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9231. Min Range: -4.9231
Max Act: 3.9543. Min Act: -0.1700
Data Index: 979369 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9231. Min Range: -4.9231
Max Act: 3.9387. Min Act: -0.1700
Data Index: 4674624 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19